@inproceedings{sulubacak-etal-2018-memad,
title = "The {M}e{MAD} Submission to the {IWSLT} 2018 Speech Translation Task",
author = {Sulubacak, Umut and
Tiedemann, J{\"o}rg and
Rouhe, Aku and
{Stig-ArneGr{\"o}nroos} and
Kurimo, Mikko},
booktitle = "Proceedings of the 15th International Conference on Spoken Language Translation",
month = oct # " 29-30",
year = "2018",
address = "Brussels",
publisher = "International Conference on Spoken Language Translation",
url = "https://aclanthology.org/2018.iwslt-1.13",
pages = "89--94",
abstract = "This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time. All of our systems start by transcribing the audio into text through an automatic speech recognition (ASR) model trained on the TED-LIUM English Speech Recognition Corpus (TED-LIUM). Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus (TED-TRANS) and the OPENSUBTITLES2018 section of the OPUS collection. In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OPENSUBTITLES2018 in training significantly improves translation performance. We also experimented with various preand postprocessing routines for the NMT module, but we did not have much success with these. Our best-scoring system attains a BLEU score of 16.45 on the test set for this year{'}s task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sulubacak-etal-2018-memad">
<titleInfo>
<title>The MeMAD Submission to the IWSLT 2018 Speech Translation Task</title>
</titleInfo>
<name type="personal">
<namePart type="given">Umut</namePart>
<namePart type="family">Sulubacak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jörg</namePart>
<namePart type="family">Tiedemann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aku</namePart>
<namePart type="family">Rouhe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Stig-ArneGrönroos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mikko</namePart>
<namePart type="family">Kurimo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-oct 29-30</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Conference on Spoken Language Translation</title>
</titleInfo>
<originInfo>
<publisher>International Conference on Spoken Language Translation</publisher>
<place>
<placeTerm type="text">Brussels</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time. All of our systems start by transcribing the audio into text through an automatic speech recognition (ASR) model trained on the TED-LIUM English Speech Recognition Corpus (TED-LIUM). Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus (TED-TRANS) and the OPENSUBTITLES2018 section of the OPUS collection. In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OPENSUBTITLES2018 in training significantly improves translation performance. We also experimented with various preand postprocessing routines for the NMT module, but we did not have much success with these. Our best-scoring system attains a BLEU score of 16.45 on the test set for this year’s task.</abstract>
<identifier type="citekey">sulubacak-etal-2018-memad</identifier>
<location>
<url>https://aclanthology.org/2018.iwslt-1.13</url>
</location>
<part>
<date>2018-oct 29-30</date>
<extent unit="page">
<start>89</start>
<end>94</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The MeMAD Submission to the IWSLT 2018 Speech Translation Task
%A Sulubacak, Umut
%A Tiedemann, Jörg
%A Rouhe, Aku
%A Kurimo, Mikko
%A Stig-ArneGrönroos
%S Proceedings of the 15th International Conference on Spoken Language Translation
%D 2018
%8 oct 29 30
%I International Conference on Spoken Language Translation
%C Brussels
%F sulubacak-etal-2018-memad
%X This paper describes the MeMAD project entry to the IWSLT Speech Translation Shared Task, addressing the translation of English audio into German text. Between the pipeline and end-to-end model tracks, we participated only in the former, with three contrastive systems. We tried also the latter, but were not able to finish our end-to-end model in time. All of our systems start by transcribing the audio into text through an automatic speech recognition (ASR) model trained on the TED-LIUM English Speech Recognition Corpus (TED-LIUM). Afterwards, we feed the transcripts into English-German text-based neural machine translation (NMT) models. Our systems employ three different translation models trained on separate training sets compiled from the English-German part of the TED Speech Translation Corpus (TED-TRANS) and the OPENSUBTITLES2018 section of the OPUS collection. In this paper, we also describe the experiments leading up to our final systems. Our experiments indicate that using OPENSUBTITLES2018 in training significantly improves translation performance. We also experimented with various preand postprocessing routines for the NMT module, but we did not have much success with these. Our best-scoring system attains a BLEU score of 16.45 on the test set for this year’s task.
%U https://aclanthology.org/2018.iwslt-1.13
%P 89-94
Markdown (Informal)
[The MeMAD Submission to the IWSLT 2018 Speech Translation Task](https://aclanthology.org/2018.iwslt-1.13) (Sulubacak et al., IWSLT 2018)
ACL
- Umut Sulubacak, Jörg Tiedemann, Aku Rouhe, Stig-ArneGrönroos, and Mikko Kurimo. 2018. The MeMAD Submission to the IWSLT 2018 Speech Translation Task. In Proceedings of the 15th International Conference on Spoken Language Translation, pages 89–94, Brussels. International Conference on Spoken Language Translation.